legado-mcp-server
Provides tools for managing RSS sources, including listing, saving, deleting, and debugging RSS feeds in a Legado reading app instance.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@legado-mcp-server debug book source for example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
legado-mcp-server
legado-mcp-server 是一个把Legado Web API封装成MCP服务的项目,主要是为了方便通过AI编写书源时调试
适用场景
把 Legado 接入 Codex、Claude Desktop、Cherry Studio 等 MCP 客户端
Related MCP server: weread-mcp
文档
环境要求
Python 3.11+
已开启 Legado Web 服务的设备
推荐使用
uv
快速开始
安装
下载源码到本地
在项目根目录下执行:
uv tool install .或者直接从 GitHub 安装:
uv tool install git+https://github.com/joestar817/legado-mcp-server.git
配置
命令行参数:
--transport:stdio或streamable-http(默认为stdio)--host:streamable-http的监听地址 (默认127.0.0.1)--port:streamable-http的监听端口 (默认8000)--legado-base-url: Legado HTTP 地址 (如http://192.168.1.10:1122)--legado-ws-url: Legado WebSocket 地址,可选 (如果不指定,默认按 HTTP 端口 + 1 推导)
环境变量:
LEGADO_BASE_URLLEGADO_WS_URLLEGADO_HTTP_TIMEOUT: HTTP 请求超时时间 (默认 60s)LEGADO_SESSION_BUFFER_SIZE: WebSocket 消息缓冲区大小 (默认 1000)
MCP 客户端接入示例
Codex
[mcp_servers.legado]
command = "legado-mcp-server"
args = ["--legado-base-url", "http://192.168.1.10:1122"]
enabled = trueLM studio
{
"mcpServers": {
"legado-mcp-server": {
"command": "legado-mcp-server",
"args": [
"--legado-base-url",
"http://192.168.1.10:1122"
]
}
}
}工具概览
完整参数和返回结构见 MCP 工具说明。
按类别概览:
书源:
book_source_getbook_source_listbook_source_savebook_source_save_manybook_source_delete_many
RSS:
rss_source_getrss_source_listrss_source_saverss_source_save_manyrss_source_delete_many
替换规则:
replace_rule_listreplace_rule_savereplace_rule_deletereplace_rule_test
图书:
book_savebook_deletebookshelf_listbook_refresh_tocbook_get_chaptersbook_get_contentbook_save_progressbook_add_local
图片与配置:
book_get_coverbook_get_imageweb_read_config_getweb_read_config_save
调试与搜索:
book_source_debugrss_source_debugbook_search
许可证
Available Tools
31 toolsbook_add_localD
Inputs: file_path (required), file_name. Returns: object
book_deleteD
Inputs: book (required). Returns: object
book_get_chaptersD
Inputs: url (required). Returns: object
book_get_contentD
Inputs: url (required), index (required). Returns: object
book_get_coverD
Inputs: path (required). Returns: object
book_get_imageD
Inputs: book_url (required), path (required), width. Returns: object
book_refresh_tocD
Inputs: url (required). Returns: object
book_saveD
Inputs: book (required). Returns: object
book_save_progressD
Inputs: progress (required). Returns: object
book_searchA
Search for books across all enabled sources and return sorted results. This tool waits for the search to complete or timeout.
Args: key: The search keyword (title or author). timeout_seconds: Maximum time to wait (multi-source search can be slow).
Inputs: key (required), timeout_seconds. Returns: object
bookshelf_listD
Inputs: no named parameters. Returns: object
book_source_debugA
Debug a book source and return all logs in one go. This is the recommended tool for book source debugging.
Args: tag: The book source URL (NOT the name). key: The keyword or URL to debug. mode: Debug mode (auto, search, detail, explore, toc, content). timeout_seconds: Maximum time to wait for the debug session to finish.
Inputs: tag (required), key (required), mode, timeout_seconds. Returns: object
book_source_delete_manyD
Inputs: sources (required). Returns: object
book_source_getD
Inputs: url (required). Returns: object
book_source_listD
Inputs: no named parameters. Returns: object
book_source_saveD
Inputs: source (required). Returns: object
book_source_save_manyD
Inputs: sources (required). Returns: object
legado_get_api_summaryA
Return the normalized summary of supported Legado HTTP and WS endpoints.
Inputs: no named parameters. Returns: object
legado_pingA
Check whether the Legado Web service is reachable.
Inputs: no named parameters. Returns: object
replace_rule_deleteD
Inputs: rule (required). Returns: object
replace_rule_listD
Inputs: no named parameters. Returns: object
replace_rule_saveD
Inputs: rule (required). Returns: object
replace_rule_testD
Inputs: rule (required), text (required). Returns: object
rss_source_debugC
Debug an RSS source and return logs in one go.
Inputs: tag (required), timeout_seconds. Returns: object
rss_source_delete_manyD
Inputs: sources (required). Returns: object
rss_source_getD
Inputs: url (required). Returns: object
rss_source_listD
Inputs: no named parameters. Returns: object
rss_source_saveD
Inputs: source (required). Returns: object
rss_source_save_manyD
Inputs: sources (required). Returns: object
web_read_config_getD
Inputs: no named parameters. Returns: object
web_read_config_saveD
Inputs: config_json (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 31 tools
Many tools have very similar names (e.g., book_source_save and book_source_save_many, rss_source_save and rss_source_save_many, etc.) and most lack descriptions, making it difficult to distinguish their distinct purposes. This ambiguity risks tool misselection by an agent.
All tool names follow a consistent <object>_<action> pattern (e.g., book_search, book_delete, book_source_save, legado_ping). No mixing of conventions (camelCase or verb styles) is observed, providing a predictable naming scheme.
With 31 tools, the server covers multiple domains (books, book sources, RSS sources, replace rules, config), which is comprehensive but on the heavier side. Some tools may be redundant (e.g., separate save and save_many), suggesting slight over-scoping.
The tool set covers core CRUD and lifecycle operations for books, sources, and rules, plus debugging and configuration. Minor gaps exist (e.g., no explicit book update tool, though book_save may serve that purpose), but overall the surface is well-rounded.
Maintenance
Related MCP Connectors
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables web-based ChatGPT and Qwen Studio to connect to local agents and projects, providing secure local file read/write, task execution, and approval workflows through a unified MCP bridge.311Apache 2.0
- AlicenseAqualityCmaintenanceEnables MCP clients to access WeChat Reading data and actions, including book search, book details, reading progress, highlights, reviews, and reading statistics, via a URL-based SSE or Streamable HTTP server.191Apache 2.0
- AlicenseCqualityBmaintenanceEnables interaction with EasyEDA Pro by exposing 760 official API methods as MCP tools, along with plugin import and browser console debugging capabilities.500Apache 2.0
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search, browse, download, organize, and post-process comics through MCP tools, including account login, favorites, comments, rankings, configuration, and download task control. Supports stdio, SSE, and HTTP transports while exposing knowledge resources for configuration and skill reference.-